初始化项目，由ModelHub XC社区提供模型

Model: mistral-experimental/pixtral-12b
Source: Original Platform

config.json

@@ -0,0 +1,40 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "../pixtral",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 1,
+  "image_token_index": 10,
+  "model_type": "llava",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "hidden_size": 5120,
+    "head_dim": 128,
+    "intermediate_size": 14336,
+    "is_composition": true,
+    "max_position_embeddings": 1024000,
+    "model_type": "mistral",
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "vision_config": {
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "image_size": 1024,
+    "is_composition": true,
+    "model_type": "pixtral",
+    "patch_size": 16,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full"
+}